d3 flash needs about 7.2 GB of memory at Q4_K_M (a 5.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 5 quants, from 0.0 GB to 9.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
d3 flash – 8.95B multimodal decision model in GGUF format
d3 flash is an 8.95B parameter model that answers typed questions about a shared state without generating text. It supports text, images and videos in a single request and returns probabilities for each option. The model is licensed under apache-2.0.
Good at
- Multimodal decision answering
- Fast inference on a single GPU
- No text generation required
Limits
- No prefix caching – each question requires a full forward pass
- Requires 8.0k context for memory estimates
- No vision support beyond images and videos
Best for
- Decision‑making pipelines
- Batching multiple choice questions
- Systems needing probability outputs
Who it’s for. Developers building decision systems that need quick, probability‑based answers to text, image, or video inputs. The model is suitable for applications that can batch questions and do not require text generation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.6 GB | Fits | Get file → | |
| Q4_K_M | 5.6 GB | 7.2 GB | Tight | Get file → | |
| Q4_K_M | 6.4 GB | 8.0 GB | Tight | Get file → | |
| Q5_K_M | 7.1 GB | 8.6 GB | Too big | Get file → | |
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K_M (5.63 GB, 7.2 GB memory at 8k context). For 12 GB VRAM, Q5_K_M (7.07 GB, 8.6 GB memory). For 16 GB VRAM, Q8_0 (9.53 GB, 11.1 GB memory). Estimates are approximate.
What GPU do you need for d3 flash?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_K_M (6.4 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (9.5 GB file, about 11.1 GB in use).
Which d3 flash quant should you choose?
Q4_K_M is the usual starting point for d3 flash: it balances file size and quality well. Here it is a 5.6 GB file.
The Q8_0 file is 9.5 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about d3 flash
How much VRAM does d3 flash need?
About 7.2 GB at Q4_K_M with an 8K context window. That is the 5.6 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run d3 flash on an 8 GB GPU?
Yes, with Q4_K_M: the 6.4 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of d3 flash GGUF?
It depends on the quant: file is 0.0 GB, Q4_K_M is 5.6 GB, Q4_K_M is 6.4 GB, Q5_K_M is 7.1 GB, Q8_0 is 9.5 GB.
What context length does d3 flash support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download d3 flash GGUF?
The files are on Hugging Face in the Livesport/d3-flash-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does d3 flash use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run d3 flash on 8 GB VRAM?
Yes, using the Q4_K_M quantized file (5.63 GB) which requires about 7.2 GB of VRAM at 8k context.
Does d3 flash support text generation?
No, it answers questions and returns probabilities without generating text.
What context length does d3 flash use?
It was trained with 262144 tokens and uses 8k context for inference.